Qwen3.6-27B

2026-10-19

RESEARCH · 1 SOURCE · arXiv cs.AI

arXiv paper: verifier feedback can both help and harm self-repair in formal theorem proving

New arXiv paper (arXiv:2610.22698v1) studies verifier-guided self-repair in Lean theorem proving using frozen Qwen3.6-27B and DeepSeek-Prover-V2-7B on MiniF2F problems. It finds that conditioning a model on its failed proof often reduces success and increases copying of the failure, while showing the compiler error can recover performance for Qwen in some settings; overall, no tested feedback condition outperforms simple instruction-only resampling under matched token budgets.

6.0

2026-10-15

RESEARCH · 1 SOURCE · arXiv cs.AI

ClawLoop: framework for self-improving harness-based LLM agents (arXiv:2610.14118v1)

arXiv preprint arXiv:2610.14118v1 introduces ClawLoop, a closed training loop for harness-based LLM agents that iteratively synthesizes tasks, trains agents (SFT/RL), and diagnoses failures to generate next-round training data without relying on an external teacher model. Using Qwen3.6-27B as the loop model, the authors report consistent gains on SkillsBench, Claw-Eval-Live, and ClawGym-Bench, and show the synthesized tasks transfer performance improvements to smaller Qwen3.5 4B and 9B models.

7.0

2026-10-12

RESEARCH · 1 SOURCE · The Decoder

Sakana AI and UC Berkeley show single LLM can self-improve via MASS but internal evaluator can reinforce blind spots

Researchers from Sakana AI and UC Berkeley introduce Multi-Agent Self-Supervision (MASS), a method where one language model runs copies of itself as sub-agents to solve, judge, and optimize workflows. Using Qwen3.6-27B as the base, the approach raised win rates versus the base model to ~70% after two rounds on several benchmarks, but shared blind spots in the model’s self-evaluation sometimes accept flawed solutions and propagate errors into subsequent training.

7.0

2026-10-09

RESEARCH · 1 SOURCE · arXiv cs.AI

On the Clock: Time‑budgeted LLM agents can adhere to deadlines but struggle to use extra time productively

arXiv:2610.10833v1 ('On the Clock') studies whether small LLM agents (Qwen3.6-27B and Qwen3-4B) can both respect explicit wall-clock time budgets and use extra time to improve performance. The authors test harness-based timing/execution enforcement and budget-aware RL (GRPO) on MLE-Bench Lite tasks and Zork I (Jericho); harness timing signals improve budget adherence, GRPO achieves near-perfect adherence and generalizes to unseen budgets on Zork I, but agents still fail to translate extra time into better task performance and often repeat actions or collapse to short-budget strategies.

6.0

2026-10-02

COMPANIES · 1 SOURCE · AWS Machine Learning

Amazon SageMaker AI demonstrates multi-turn reinforcement learning (MTRL) fine-tuning for search agents with Qwen3.6-27B

Amazon’s blog post describes using Amazon SageMaker AI’s multi-turn reinforcement learning (MTRL) capability to fine-tune a Qwen3.6-27B model for an LLM-powered search agent. The write-up details MTRL features—serverless execution, modular agent-environment interfaces, asynchronous rollouts, built-in algorithms (PPO, CISPO, IS), trajectory observability via MLflow, and evaluation jobs—and shows an enterprise search use case combining BM25 and vector search tools.

6.0

2026-09-16

MODELS · 1 SOURCE · NVIDIA Developer

TensorRT Edge-LLM runs Qwen3.6-27B on Jetson AGX Thor, completes MLPerf Edge Agentic 6.4× faster

NVIDIA's TensorRT Edge-LLM ran Qwen3.6-27B on a single Jetson AGX Thor Developer Kit and achieved 52.33 tokens/sec in the MLPerf Inference v6.1 Edge Agentic performance workload, completing all 1,007 turns in 24 minutes 36 seconds — 6.4× faster than the llama.cpp Jetson reference (2h37m). The submission used NVFP4 quantization for weights/activations, FP8 for the KV cache, tree-based multi-token prediction, and KV-cache/recurrent-state reuse to accelerate long-context agent decoding.

7.0